Instructions to use julienp79/occitan-gemma-3-4b-it-dora-sfttrainer with libraries, inference providers, notebooks, and local apps. Follow these links to get started.

Libraries
PEFT
How to use julienp79/occitan-gemma-3-4b-it-dora-sfttrainer with PEFT:
```
Task type is invalid.
```

How to use julienp79/occitan-gemma-3-4b-it-dora-sfttrainer with Transformers:

# Use a pipeline as a high-level helper
from transformers import pipeline

pipe = pipeline("text-generation", model="julienp79/occitan-gemma-3-4b-it-dora-sfttrainer")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
pipe(text=messages)

# Load model directly
from transformers import AutoProcessor, AutoModelForMultimodalLM

processor = AutoProcessor.from_pretrained("julienp79/occitan-gemma-3-4b-it-dora-sfttrainer")
model = AutoModelForMultimodalLM.from_pretrained("julienp79/occitan-gemma-3-4b-it-dora-sfttrainer", device_map="auto")
messages = [
    {
        "role": "user",
        "content": [
            {"type": "image", "url": "https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/p-blog/candy.JPG"},
            {"type": "text", "text": "What animal is on the candy?"}
        ]
    },
]
inputs = processor.apply_chat_template(
	messages,
	add_generation_prompt=True,
	tokenize=True,
	return_dict=True,
	return_tensors="pt",
).to(model.device)

outputs = model.generate(**inputs, max_new_tokens=40)
print(processor.decode(outputs[0][inputs["input_ids"].shape[-1]:]))

Notebooks
Google Colab
Kaggle
Local Apps Settings

llama.cpp

How to use julienp79/occitan-gemma-3-4b-it-dora-sfttrainer with llama.cpp:

Install (macOS, Linux)

curl -LsSf https://llama.app/install.sh | sh
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf julienp79/occitan-gemma-3-4b-it-dora-sfttrainer:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf julienp79/occitan-gemma-3-4b-it-dora-sfttrainer:Q4_K_M

Install from WinGet (Windows)

winget install llama.cpp
# Start a local OpenAI-compatible server with a web UI:
llama serve -hf julienp79/occitan-gemma-3-4b-it-dora-sfttrainer:Q4_K_M
# Run inference directly in the terminal:
llama cli -hf julienp79/occitan-gemma-3-4b-it-dora-sfttrainer:Q4_K_M

Use pre-built binary

# Download pre-built binary from:
# https://github.com/ggerganov/llama.cpp/releases
# Start a local OpenAI-compatible server with a web UI:
./llama-server -hf julienp79/occitan-gemma-3-4b-it-dora-sfttrainer:Q4_K_M
# Run inference directly in the terminal:
./llama-cli -hf julienp79/occitan-gemma-3-4b-it-dora-sfttrainer:Q4_K_M

Build from source code

git clone https://github.com/ggerganov/llama.cpp.git
cd llama.cpp
cmake -B build
cmake --build build -j --target llama-server llama-cli
# Start a local OpenAI-compatible server with a web UI:
./build/bin/llama-server -hf julienp79/occitan-gemma-3-4b-it-dora-sfttrainer:Q4_K_M
# Run inference directly in the terminal:
./build/bin/llama-cli -hf julienp79/occitan-gemma-3-4b-it-dora-sfttrainer:Q4_K_M

Use Docker

docker model run hf.co/julienp79/occitan-gemma-3-4b-it-dora-sfttrainer:Q4_K_M

LM Studio
Jan

vLLM

How to use julienp79/occitan-gemma-3-4b-it-dora-sfttrainer with vLLM:

Install from pip and serve model

# Install vLLM from pip:
pip install vllm
# Start the vLLM server:
vllm serve "julienp79/occitan-gemma-3-4b-it-dora-sfttrainer"
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:8000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "julienp79/occitan-gemma-3-4b-it-dora-sfttrainer",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker

docker model run hf.co/julienp79/occitan-gemma-3-4b-it-dora-sfttrainer:Q4_K_M

SGLang

How to use julienp79/occitan-gemma-3-4b-it-dora-sfttrainer with SGLang:

Install from pip and serve model

# Install SGLang from pip:
pip install sglang
# Start the SGLang server:
python3 -m sglang.launch_server \
    --model-path "julienp79/occitan-gemma-3-4b-it-dora-sfttrainer" \
    --host 0.0.0.0 \
    --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "julienp79/occitan-gemma-3-4b-it-dora-sfttrainer",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Use Docker images

docker run --gpus all \
    --shm-size 32g \
    -p 30000:30000 \
    -v ~/.cache/huggingface:/root/.cache/huggingface \
    --env "HF_TOKEN=<secret>" \
    --ipc=host \
    lmsysorg/sglang:latest \
    python3 -m sglang.launch_server \
        --model-path "julienp79/occitan-gemma-3-4b-it-dora-sfttrainer" \
        --host 0.0.0.0 \
        --port 30000
# Call the server using curl (OpenAI-compatible API):
curl -X POST "http://localhost:30000/v1/chat/completions" \
	-H "Content-Type: application/json" \
	--data '{
		"model": "julienp79/occitan-gemma-3-4b-it-dora-sfttrainer",
		"messages": [
			{
				"role": "user",
				"content": "What is the capital of France?"
			}
		]
	}'

Ollama
How to use julienp79/occitan-gemma-3-4b-it-dora-sfttrainer with Ollama:
```
ollama run hf.co/julienp79/occitan-gemma-3-4b-it-dora-sfttrainer:Q4_K_M
```

Unsloth Studio

How to use julienp79/occitan-gemma-3-4b-it-dora-sfttrainer with Unsloth Studio:

Install Unsloth Studio (macOS, Linux, WSL)

curl -fsSL https://unsloth.ai/install.sh | sh
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for julienp79/occitan-gemma-3-4b-it-dora-sfttrainer to start chatting

Install Unsloth Studio (Windows)

irm https://unsloth.ai/install.ps1 | iex
# Run unsloth studio
unsloth studio -H 0.0.0.0 -p 8888
# Then open http://localhost:8888 in your browser
# Search for julienp79/occitan-gemma-3-4b-it-dora-sfttrainer to start chatting

Using HuggingFace Spaces for Unsloth

# No setup required
# Open https://huggingface.co/spaces/unsloth/studio in your browser
# Search for julienp79/occitan-gemma-3-4b-it-dora-sfttrainer to start chatting

Docker Model Runner
How to use julienp79/occitan-gemma-3-4b-it-dora-sfttrainer with Docker Model Runner:
```
docker model run hf.co/julienp79/occitan-gemma-3-4b-it-dora-sfttrainer:Q4_K_M
```

Lemonade

How to use julienp79/occitan-gemma-3-4b-it-dora-sfttrainer with Lemonade:

Pull the model

# Download Lemonade from https://lemonade-server.ai/
lemonade pull julienp79/occitan-gemma-3-4b-it-dora-sfttrainer:Q4_K_M

Run and chat with the model

lemonade run user.occitan-gemma-3-4b-it-dora-sfttrainer-Q4_K_M

List all available models

lemonade list

Atomic Chat

Occitan Gemma 3 4B IT (DoRA, Merged)

This repository contains a fine-tuned version of Google's Gemma 3 4B Instruct optimized for the Occitan language using DoRA (Weight-Decomposed Low-Rank Adaptation).

Repository Structure

Root Directory: Full merged Safetensors weights (bfloat16, compatible with transformers)
adapter/ Folder: The raw DoRA adapter files (for use with PEFT)
gguf/ Folder: Quantized GGUF versions (f16, Q2_K, Q4_K_M, Q5_K_M, Q8_0) for local inference via llama.cpp, LM Studio, Ollama, etc.

Usage

Using the merged model (Transformers)

from transformers import AutoModelForCausalLM, AutoTokenizer

model_id = "julienp79/occitan-gemma-3-4b-it-dora-sfttrainer"

tokenizer = AutoTokenizer.from_pretrained(model_id)
model = AutoModelForCausalLM.from_pretrained(model_id, device_map="auto")

messages = [
    {"role": "user", "content": "Escrivètz un cort paragraf en occitan sus la lenga occitana e son importància."},
]

inputs = tokenizer.apply_chat_template(messages, add_generation_prompt=True, return_tensors="pt").to(model.device)
outputs = model.generate(inputs, max_new_tokens=256)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Using the DoRA adapter with PEFT

from peft import PeftModel
from transformers import AutoModelForCausalLM, AutoTokenizer

base_model = AutoModelForCausalLM.from_pretrained(
    "unsloth/gemma-3-4b-it",
    device_map="auto",
    torch_dtype="auto"
)
tokenizer = AutoTokenizer.from_pretrained("unsloth/gemma-3-4b-it")

# Load adapter from the adapter/ subfolder
model = PeftModel.from_pretrained(base_model, "julienp79/occitan-gemma-3-4b-it-dora-sfttrainer", subfolder="adapter")
model.eval()

prompt = tokenizer.apply_chat_template(
    [{"role": "user", "content": "Sètz un assistent utila que parla occitan."}],
    tokenize=False,
    add_generation_prompt=True
)
inputs = tokenizer(prompt, return_tensors="pt").to("cuda")
outputs = model.generate(**inputs, max_new_tokens=128)
print(tokenizer.decode(outputs[0], skip_special_tokens=True))

Using GGUF quantizations (llama.cpp)

llama-cli -hf julienp79/occitan-gemma-3-4b-it-dora-sfttrainer:Q4_K_M \
  -p "<start_of_turn>user\nEscrivètz un cort paragraf en occitan.<end_of_turn>\n<start_of_turn>model\n" \
  -n 256 -e --temp 0.7

Or via the GGUF file directly:

llama-cli -m gguf/occitan-gemma-3-4b-it-dora-sfttrainer-Q4_K_M.gguf \
  -p "<start_of_turn>user\nEscrivètz un cort paragraf en occitan.<end_of_turn>\n<start_of_turn>model\n" \
  -n 256 -e --temp 0.7

Adapter Details

Adapter Type: DoRA (Weight-Decomposed Low-Rank Adaptation, use_dora=True)
Base Model: unsloth/gemma-3-4b-it (Google Gemma 3 4B Instruct)
LoRA Rank (r): 16
LoRA Alpha: 32
Target Modules: q_proj, k_proj, v_proj, o_proj, gate_proj, up_proj, down_proj
Dropout: 0
Training Method: SFT (Supervised Fine-Tuning) with SFTTrainer

Training Details

Block Size: 768 tokens
Learning Rate: 1e-4 (cosine schedule)
Optimizer: Paged AdamW 8-bit
Max Gradient Norm: 1.0
Warmup Steps: 200
Weight Decay: 0.01
Epochs: 5
Total Steps: ~950
Hardware: RTX 3060 12GB (4-bit base model with Unsloth's gradient checkpointing)

Training procedure

This model was trained with SFT (Supervised Fine-Tuning) using SFTTrainer on raw Occitan text (literary, journalistic, grammar, and encyclopedic sources). No chat templating was applied during training — the model learns language structure via causal language modeling on chunked text.